From c4ad8f98bef77c7356aa6a9ad9188a6acc6b849d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 5 Feb 2014 12:54:53 -0800 Subject: execve: use 'struct filename *' for executable name passing This changes 'do_execve()' to get the executable name as a 'struct filename', and to free it when it is done. This is what the normal users want, and it simplifies and streamlines their error handling. The controlled lifetime of the executable name also fixes a use-after-free problem with the trace_sched_process_exec tracepoint: the lifetime of the passed-in string for kernel users was not at all obvious, and the user-mode helper code used UMH_WAIT_EXEC to serialize the pathname allocation lifetime with the execve() having finished, which in turn meant that the trace point that happened after mm_release() of the old process VM ended up using already free'd memory. To solve the kernel string lifetime issue, this simply introduces "getname_kernel()" that works like the normal user-space getname() function, except with the source coming from kernel memory. As Oleg points out, this also means that we could drop the tcomm[] array from 'struct linux_binprm', since the pathname lifetime now covers setup_new_exec(). That would be a separate cleanup. Reported-by: Igor Zhbanov Tested-by: Steven Rostedt Cc: Oleg Nesterov Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c5981..d79678c188a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2079,6 +2079,7 @@ extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname(const char __user *); +extern struct filename *getname_kernel(const char *); enum { FILE_CREATED = 1, -- cgit v1.2.3-70-g09d2 From d311d79de305f1ada47cadd672e6ed1b28a949eb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 9 Feb 2014 15:18:09 -0500 Subject: fix O_SYNC|O_APPEND syncing the wrong range on write() It actually goes back to 2004 ([PATCH] Concurrent O_SYNC write support) when sync_page_range() had been introduced; generic_file_write{,v}() correctly synced pos_after_write - written .. pos_after_write - 1 but generic_file_aio_write() synced pos_before_write .. pos_before_write + written - 1 instead. Which is not the same thing with O_APPEND, obviously. A couple of years later correct variant had been killed off when everything switched to use of generic_file_aio_write(). All users of generic_file_aio_write() are affected, and the same bug has been copied into other instances of ->aio_write(). The fix is trivial; the only subtle point is that generic_write_sync() ought to be inlined to avoid calculations useless for the majority of calls. Signed-off-by: Al Viro --- fs/cifs/file.c | 4 ++-- fs/ext4/file.c | 2 +- fs/ntfs/file.c | 2 +- fs/sync.c | 17 ----------------- fs/xfs/xfs_file.c | 2 +- include/linux/fs.h | 8 +++++++- mm/filemap.c | 4 ++-- 7 files changed, 14 insertions(+), 25 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 853d6d1cc82..a7eda8ebfac 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2559,8 +2559,8 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov, if (rc > 0) { ssize_t err; - err = generic_write_sync(file, pos, rc); - if (err < 0 && rc > 0) + err = generic_write_sync(file, iocb->ki_pos - rc, rc); + if (err < 0) rc = err; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 43e64f6022e..1a5073959f3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -152,7 +152,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, if (ret > 0) { ssize_t err; - err = generic_write_sync(file, pos, ret); + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0 && ret > 0) ret = err; } diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index ea4ba9daeb4..db9bd8a3172 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2134,7 +2134,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0) { - int err = generic_write_sync(file, pos, ret); + int err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } diff --git a/fs/sync.c b/fs/sync.c index f1553745223..e8ba024a055 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -222,23 +222,6 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd) return do_fsync(fd, 1); } -/** - * generic_write_sync - perform syncing after a write if file / inode is sync - * @file: file to which the write happened - * @pos: offset where the write started - * @count: length of the write - * - * This is just a simple wrapper about our general syncing function. - */ -int generic_write_sync(struct file *file, loff_t pos, loff_t count) -{ - if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host)) - return 0; - return vfs_fsync_range(file, pos, pos + count - 1, - (file->f_flags & __O_SYNC) ? 0 : 1); -} -EXPORT_SYMBOL(generic_write_sync); - /* * sys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 2e7989e3a2d..64b48eade91 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -799,7 +799,7 @@ xfs_file_aio_write( XFS_STATS_ADD(xs_write_bytes, ret); /* Handle various SYNC-type writes */ - err = generic_write_sync(file, pos, ret); + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c5981..75ff961be05 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2273,7 +2273,13 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); -extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); +static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count) +{ + if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host)) + return 0; + return vfs_fsync_range(file, pos, pos + count - 1, + (file->f_flags & __O_SYNC) ? 0 : 1); +} extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK diff --git a/mm/filemap.c b/mm/filemap.c index d56d3c145b9..7a13f6ac542 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2553,8 +2553,8 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (ret > 0) { ssize_t err; - err = generic_write_sync(file, pos, ret); - if (err < 0 && ret > 0) + err = generic_write_sync(file, iocb->ki_pos - ret, ret); + if (err < 0) ret = err; } return ret; -- cgit v1.2.3-70-g09d2